paper-with-me

Papers

Towards Generalizable Scene Change Detection

2024-09-10 · Jaewoo Kim, UeHwan Kim

Scene Change Detection (SCD) is vital for applications such as visual surveillance and mobile robotics. However, current SCD methods exhibit a bias to the temporal order of training datasets and limited performance on unseen domains; coventional SCD benchmarks are not able to evaluate generalization or temporal consistency. To tackle these limitations, we introduce a Generalizable Scene Change Detection Framework (GeSCF) in this work. The proposed GeSCF leverages localized semantics of a foundation model without any re-training or fine-tuning -- for generalization over unseen domains. Specifically, we design an adaptive thresholding of the similarity distribution derived from facets of the pre-trained foundation model to generate initial pseudo-change mask. We further utilize Segment Anything Model's (SAM) class-agnostic masks to refine pseudo-masks. Moreover, our proposed framework maintains commutative operations in all settings to ensure complete temporal consistency. Finally, we define new metrics, evaluation dataset, and evaluation protocol for Generalizable Scene Change Detection (GeSCD). Extensive experiments demonstrate that GeSCF excels across diverse and challenging environments -- establishing a new benchmark for SCD performance.

📄 PDF Abstract BibTeX arXiv:2409.06214

Code (1)

1124jaewookim/towards-generalizable-scene-change-detection 공식 구현 pytorch

Tasks

Change DetectionScene Change Detection

Similar Papers 제목 키워드 기반

Towards Generalizable Scene Change Detection

2025-01-01 · CVPR 2025 1 · Jae-Woo Kim, Ue-Hwan Kim

While current state-of-the-art Scene Change Detection (SCD) approaches achieve impressive results in well-trained research data, they become unreliable under unseen environments and different temporal conditions; in-…

Change DetectionScene Change Detection

Leveraging Geometric Priors for Unaligned Scene Change Detection

2025-09-14 · Ziling Liu, Ziwei Chen, Mingqi Gao, Jinyu Yang 외 arxiv

Unaligned Scene Change Detection aims to detect scene changes between image pairs captured at different times without assuming viewpoint alignment. To handle viewpoint variations, current methods rely solely on 2D visual…

Scene Change Detection

G3R: Gradient Guided Generalizable Reconstruction

2024-09-28 · Yun Chen, Jingkang Wang, Ze Yang, Sivabalan Manivasagam 외

Large scale 3D scene reconstruction is important for applications such as virtual reality and simulation. Existing neural rendering approaches (e.g., NeRF, 3DGS) have achieved realistic reconstructions on large scenes, b…

3DGS3D Scene ReconstructionNeRFNeural Rendering

Adjustable Visual Appearance for Generalizable Novel View Synthesis

2023-06-02 · Josef Bengtson, David Nilsson, Che-Tsung Lin, Marcel Büsching 외

We present a generalizable novel view synthesis method which enables modifying the visual appearance of an observed scene so rendered views match a target weather or lighting condition without any scene specific training…

Generalizable Novel View SynthesisNovel View SynthesisStyle Transfer

Understanding Cross-Sensor Feature Variations for Generalizable 3D Perception

2026-06-10 · Xin Qiu, Wenjie Liu, Fuyuan Ai, YuChen Tan 외 arxiv

Radar-camera BEV perception often suffers from degraded performance when evaluated across datasets, as changes in driving scenes, sensor configurations, and environmental conditions can alter both the input observations …